Gebruikersprofielen voor author:"Mudrakarta Pramod"

Pramod Kaushik Mudrakarta

Google Research
Geverifieerd e-mailadres voor google.com
Geciteerd door 188

Did the model understand the question?

PK Mudrakarta, A Taly, M Sundararajan… - arXiv preprint arXiv …, 2018 - arxiv.org
We analyze state-of-the-art deep learning models for three tasks: question answering on (1)
images,(2) tables, and (3) passages of text. Using the notion of\emph {attribution}(word
importance), we find that these deep networks often ignore important question terms …

K for the price of 1: Parameter-efficient multi-task and transfer learning

PK Mudrakarta, M Sandler, A Zhmoginov… - arXiv preprint arXiv …, 2018 - arxiv.org
We introduce a novel method that enables parameter-efficient transfer and multi-task
learning with deep neural networks. The basic approach is to learn a model patch-a small
set of parameters-that will specialize to each task, instead of fine-tuning the last layer or the …

Multiresolution matrix compression

N Teneva, PK Mudrakarta… - Artificial Intelligence and …, 2016 - proceedings.mlr.press
Abstract Multiresolution Matrix Factorization (MMF) is a recently introduced method for
finding multiscale structure and defining wavelets on graphs and matrices. MMF can also be
used for matrix compression (sketching). However, the original MMF algorithm of (Kondor et …

It was the training data pruning too!

PK Mudrakarta, A Taly, M Sundararajan… - arXiv preprint arXiv …, 2018 - arxiv.org
We study the current best model (KDG) for question answering on tabular data evaluated
over the WikiTableQuestions dataset. Previous ablation studies performed against this
model attributed the model's performance to certain aspects of its architecture. In this paper …

[PDF][PDF] Tight Continuous Relaxation of the Balanced k-Cut Problem.

SS Rangapuram, PK Mudrakarta, M Hein - NIPS, 2014 - ml.uni-saarland.de
Spectral Clustering as a relaxation of the normalized/ratio cut has become one of the
standard graph-based clustering methods. Existing methods for the computation of multiple
clusters, corresponding to a balanced k-cut of the graph, are either based on greedy …

Parallel mmf: a multiresolution approach to matrix computation

R Kondor, N Teneva, PK Mudrakarta - arXiv preprint arXiv:1507.04396, 2015 - arxiv.org
Multiresolution Matrix Factorization (MMF) was recently introduced as a method for finding
multiscale structure and defining wavelets on graphs/matrices. In this paper we derive
pMMF, a parallel algorithm for computing the MMF factorization. Empirically, the running …

Oqtans: the RNA-seq workbench in the cloud for complete and reproducible quantitative transcriptome analysis

VT Sreedharan, SJ Schultheiss, G Jean… - …, 2014 - academic.oup.com
We present Oqtans, an open-source workbench for quantitative transcriptome analysis, that
is integrated in Galaxy. Its distinguishing features include customizable computational
workflows and a modular pipeline architecture that facilitates comparative assessment of …

A generic multiresolution preconditioner for sparse symmetric systems

PK Mudrakarta, R Kondor - arXiv preprint arXiv:1707.02054, 2017 - arxiv.org
We introduce a new general purpose multiresolution preconditioner for symmetric linear
systems. Most existing multiresolution preconditioners use some standard wavelet basis that
relies on knowledge of the geometry of the underlying domain. In constrast, based on the …

Oqtans: a Galaxy-integrated workflow for quantitative transcriptome analysis from NGS Data

SJ Schultheiss, G Jean, J Behr, R Bohnert, P Drewe… - BMC …, 2011 - Springer
Background The current revolution in sequencing technologies allows us to obtain a much
more detailed picture of transcriptomes via RNA-Sequencing. We have developed the first
integrative online platform, oqtans, for quantitatively analyzing RNA-Seq experiments. Our …

mTim: rapid and accurate transcript reconstruction from RNA-Seq data

G Zeller, N Goernitz, A Kahles, J Behr… - arXiv preprint arXiv …, 2013 - arxiv.org
Recent advances in high-throughput cDNA sequencing (RNA-Seq) technology have
revolutionized transcriptome studies. A major motivation for RNA-Seq is to map the structure
of expressed transcripts at nucleotide resolution. With accurate computational tools for …